prikaz prve stranice dokumenta Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake
  Download
PDF 2.91 MB
master's thesis
Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake
2019. urn:nbn:hr:200:762512
Špoljar, Domagoj
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Multimedia Systems and Digital Television

Cite this document

Špoljar, D. (2019). Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:762512

Špoljar, Domagoj. "Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:762512

Špoljar, Domagoj. "Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2019. https://urn.nsk.hr/urn:nbn:hr:200:762512

Špoljar, D. (2019). 'Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 18 January 2021, https://urn.nsk.hr/urn:nbn:hr:200:762512

Špoljar D. Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2019 [cited 2021 January 18] Available at: https://urn.nsk.hr/urn:nbn:hr:200:762512

D. Špoljar, "Detekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:200:762512

Islandora Bookmark - Please login to use this feature
Metadata
TitleDetekcija voznih traka ispred vozila pomoću kamere i upozoravanje na nepoželjno napuštanje trake
Title (english)Lane detection and lane departure warning using front view camera in vehicle
AuthorDomagoj Špoljar
MentorMario Vranješ (mentor)
MentorDenis Vranješ (mentor)
Committee memberMario Vranješ (predsjednik povjerenstva)
Committee memberMarijan Herceg (član povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Multimedia Systems and Digital Television)
Osijek
Defense date and country2019-09-18, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
U sklopu ovog diplomskog rada izrađen je računalni algoritma za detekciju voznih traka na cesti ispred vozila u slici dobivenoj s kamere na prednjem kraju vozila i upozorenje vozača na napuštanje vozne trake. Kompletan računalni program sastoji se od osam koraka obrade izvorne slike, koji daju informacije o broju detektiranih linija voznih traka u slici te njihovom položaju na slici. Obrada slike se vrši za svaki okvir u snimci zasebno. Algoritam koristi metode računalnog vida pomoću implementacije OpenCV biblioteke. Kompletan algoritam je izrađen u Python programskom okruženju s dodatkom OpenCV i NumPy biblioteka. Testiranjem izrađenog algoritma na raznim snimkama snimljenih pomoću kamere na prednjem kraju vozila u različitim vremenskim uvjetima i s pojavama raznih vrsta linija voznih traka, zaključeno je da je algoritam prilagodljiv na razne vremenske uvjete, doba dana ili izgled prometnih linija. Također, rezultati testiranja pokazali su i određene manjkavosti algoritma i prostor za potencijalna buduća poboljšanja.
Abstract (english)
As part of this diploma paper, a computer algorithm was developed for the lane detection on the road with the image obtained from the camera at the front end of the vehicle with addition to warn the driver against unwanted lane departure. The complete computer program consists of seven steps of processing the original image, which provide information on the number of detected lane lines in the image and their position on the image. Image processing is done for each frame in the video separately. The algorithm uses computer vision methods using an OpenCV library implementation. The complete algorithm was created in a Python programming environment with the addition of OpenCV and NumPy libraries. Testing the developed algorithm on various shots taken at the front end of the vehicle in different weather conditions and with the appearance of different types of lanes, it was concluded that the algorithm is adaptable to different weather conditions, time of day or the appearance of traffic lines recorded by the camera at the front end of the car. Also, the test results showed some weaknesses in the algorithm and room for potential future improvements.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:762512
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2019-12-24 06:28:15